© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 41234
    Prev
    Next
    INDEX
    Explanations

    file or mk post

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anner
    -0.08
    ãģ¦ãĤĭ
    -0.07
    æŁ
    -0.07
    ires
    -0.07
    endor
    -0.07
    Ç
    -0.07
    éĢļ讯åijĺ
    -0.07
     pictured
    -0.07
    ç©Ĺ
    -0.07
     mirac
    -0.07
    POSITIVE LOGITS
    beau
    0.07
    åĬ©æīĭ
    0.07
    åĬłåĭĴ
    0.06
    åŃľ
    0.06
    .cx
    0.06
    PLACE
    0.06
    æĻĸ
    0.06
    ptica
    0.06
    åĸµåĸµ
    0.06
     Scratch
    0.06
    Activations Density 0.007%

    No Known Activations